© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15837
    Prev
    Next
    INDEX
    Explanations

    words from formal documents, especially those related to contracts and guarantees

    oai_token-act-pair · gemini-2.0-flash

    technical/legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    era
    -0.58
    u
    -0.57
    ra
    -0.56
    ira
    -0.56
    ju
    -0.53
    ja
    -0.53
    at
    -0.53
    il
    -0.51
    ke
    -0.50
    j
    -0.50
    POSITIVE LOGITS
    I
    0.72
    O
    0.70
    OE
    0.69
    fromnode
    0.68
    ED
    0.67
    ES
    0.67
    A
    0.66
    AO
    0.66
    AAS
    0.63
    E
    0.63
    Activations Density 2.309%

    No Known Activations